Sciweavers

573 search results - page 71 / 115
» Evolutionary functional testing of continuous control system...
Sort
View
NIPS
1996
15 years 2 months ago
Multidimensional Triangulation and Interpolation for Reinforcement Learning
Dynamic Programming, Q-learning and other discrete Markov Decision Process solvers can be applied to continuous d-dimensional state-spaces by quantizing the state space into an arr...
Scott Davies
GECCO
2005
Springer
138views Optimization» more  GECCO 2005»
15 years 6 months ago
Artificial immune system for solving generalized geometric problems: a preliminary results
Generalized geometric programming (GGP) is an optimization method in which the objective function and constraints are nonconvex functions. Thus, a GGP problem includes multiple lo...
Jui-Yu Wu, Yun-Kung Chung
CG
2002
Springer
15 years 17 days ago
Gentropy: evolving 2D textures
Gentropy is a genetic programming system that evolves two-dimensional procedural textures. It synthesizes textures by combining mathematical and image manipulation functions into ...
Andrea L. Wiens, Brian J. Ross
102
Voted
NECO
2007
115views more  NECO 2007»
15 years 7 days ago
Training Recurrent Networks by Evolino
In recent years, gradient-based LSTM recurrent neural networks (RNNs) solved many previously RNN-unlearnable tasks. Sometimes, however, gradient information is of little use for t...
Jürgen Schmidhuber, Daan Wierstra, Matteo Gag...
CDC
2009
IEEE
116views Control Systems» more  CDC 2009»
15 years 4 months ago
On the linear-exponential filtering problem for general Gaussian processes
The explicit solution of the filtering problem with exponential criteria for a general Gaussian signal is obtained through an approach which is based on a conditional Cameron-Mart...
Marina L. Kleptsyna, Alain Le Breton, Michel Viot